Navigating electronic documents using domain discourse trees

Abstract

Navigating text using an extended discourse tree. In an example, a method accesses an extended discourse tree that includes a first discourse tree for a first document and a second discourse tree for a second document. The method determines a first elementary discourse unit that is responsive to a query from a user device and a corresponding first position. The method further determines a set of navigation options including a first rhetorical relationship between the first elementary discourse unit and a second elementary discourse unit of the first discourse tree and a second rhetorical relationship between the first elementary discourse unit and a third elementary discourse unit of the second discourse tree. The method presents the rhetorical relationships to a user device. Responsive to receiving, from a user device, a selection of a rhetorical relationship, the method presents a corresponding elementary discourse unit to the user device.

What is claimed is: 
     
       1. A computer-implemented method for determining a rhetorical relationship between one or more documents, the method comprising:
 accessing a first discourse tree representing a first document of a set of documents and a second discourse tree representing a second document from the set of documents; 
 obtaining a reference extended discourse tree from a set of extended discourse trees, the obtaining comprising:
 applying the first discourse tree and the second discourse tree to a trained machine-learning model, wherein the trained machine-learning model iterates through the set of extended discourse trees to identify discourse tress from the set of extended discourse trees; and 
 receiving, from the trained machine-learning model, an identification of (i) a first candidate discourse tree and (ii) a second candidate discourse tree, wherein the first candidate discourse tree and the second candidate discourse tree are a best match for the first discourse tree and the second discourse tree; 
 
 determining, from the reference extended discourse tree, one or more links between the first candidate discourse tree and the second candidate discourse tree; and 
 propagating the one or more links to the first discourse tree and the second discourse tree, thereby creating an extended discourse tree. 
 
     
     
       2. The computer-implemented method of  claim 1 , wherein the first discourse tree and the second discourse tree are created by:
 accessing a sentence comprising a plurality of fragments, wherein at least one fragment comprises a verb and a plurality of words, each word comprising a role of the word within the fragment, wherein each fragment is an elementary discourse unit; and 
 generating a discourse tree that represents rhetorical relationships between the plurality of fragments, wherein the discourse tree comprises a plurality of nodes, each nonterminal node representing a respective rhetorical relationship between two of the plurality of fragments, each terminal node of the nodes of the discourse tree is associated with one of the plurality of fragments. 
 
     
     
       3. The computer-implemented method of  claim 1 , further comprising:
 determining, based on the one or more links, one or more rhetorical relationships between the first discourse tree and the extended discourse tree; and 
 presenting the rhetorical relationships to a user device. 
 
     
     
       4. The computer-implemented method of  claim 3 , wherein each rhetorical relationship of the rhetorical relationships comprises one of (i) elaboration, (ii) enablement, (iii) condition, (iv) contrast, or (v) attribution. 
     
     
       5. The computer-implemented method of  claim 1 , wherein the first document and the second document are obtained by executing a user query of one or more documents. 
     
     
       6. The computer-implemented method of  claim 1 , wherein the first document and the second document include text based on a particular topic. 
     
     
       7. The computer-implemented method of  claim 1 , wherein a difference between (i) a first content score for the first document and (ii) a second content score for the second document is within a threshold. 
     
     
       8. A system comprising:
 a non-transitory computer-readable medium storing computer-executable program instructions; and 
 a processing device communicatively coupled to the non-transitory computer-readable medium for executing the computer-executable program instructions, wherein executing the computer-executable program instructions configures the processing device to perform operations comprising:
 accessing a first discourse tree representing a first document of a set of documents and a second discourse tree representing a second document from the set of documents; 
 obtaining a reference extended discourse tree from a set of extended discourse trees, the obtaining comprising:
 applying the first discourse tree and the second discourse tree to a trained machine-learning model, wherein the trained machine-learning model iterates through the set of extended discourse trees to identify discourse trees from the set of extended discourse trees; and 
 receiving, from the trained machine-learning model, an identification of (i) a first candidate discourse tree and (ii) a second candidate discourse tree, wherein the first candidate discourse tree and the second candidate discourse tree are a best match for the first discourse tree and the second discourse tree; 
 
 determining, from the reference extended discourse tree, one or more links between the first candidate discourse tree and the second candidate discourse tree; and 
 propagating the one or more links to the first discourse tree and the second discourse tree, thereby creating an extended discourse tree. 
 
 
     
     
       9. The system of  claim 8 , wherein the first discourse tree and the second discourse tree are created by:
 accessing a sentence comprising a plurality of fragments, wherein at least one fragment comprises a verb and a plurality of words, each word comprising a role of the word within the fragment, wherein each fragment is an elementary discourse unit; and 
 generating a discourse tree that represents rhetorical relationships between the plurality of fragments, wherein the discourse tree comprises a plurality of nodes, each nonterminal node representing a respective rhetorical relationship between two of the plurality of fragments, each terminal node of the nodes of the discourse tree is associated with one of the plurality of fragments. 
 
     
     
       10. The system of  claim 8 , further comprising:
 determining, based on the one or more links, one or more rhetorical relationships between the first discourse tree and the extended discourse tree; and 
 presenting the rhetorical relationships to a user device. 
 
     
     
       11. The system of  claim 10 , wherein each rhetorical relationship of the rhetorical relationships comprises one of (i) elaboration, (ii) enablement, (iii) condition, (iv) contrast, or (v) attribution. 
     
     
       12. The system of  claim 8 , wherein the first document and the second document are obtained by executing a user query of one or more documents. 
     
     
       13. The system of  claim 8 , wherein the first document and the second document include text based on a particular topic. 
     
     
       14. The system of  claim 8 , wherein a difference between (i) a first content score for the first document and (ii) a second content score for the second document is within a threshold. 
     
     
       15. A non-transitory computer-readable storage medium storing computer-executable program instructions, wherein when executed by a processing device, the computer-executable program instructions cause the processing device to perform operations comprising:
 accessing a first discourse tree representing a first document of a set of documents and a second discourse tree representing a second document from the set of documents; 
 obtaining a reference extended discourse tree from a set of extended discourse trees, the obtaining comprising: 
 applying the first discourse tree and the second discourse tree to a trained machine-learning model, wherein the trained machine-learning model iterates through the set of extended discourse trees to identify discourse trees from the set of extended discourse trees; and 
 receiving, from the trained machine-learning model, an identification of (i) a first candidate discourse tree and (ii) a second candidate discourse tree, wherein the first candidate discourse tree and the second candidate discourse tree are a best match for the first discourse tree and the second discourse tree; 
 determining, from the reference extended discourse tree, one or more links between the first candidate discourse tree and the second candidate discourse tree; and 
 propagating the one or more links to the first discourse tree and the second discourse tree, thereby creating an extended discourse tree. 
 
     
     
       16. The non-transitory computer-readable storage medium of  claim 15 , wherein the first discourse tree and the second discourse tree are created by:
 accessing a sentence comprising a plurality of fragments, wherein at least one fragment comprises a verb and a plurality of words, each word comprising a role of the word within the fragment, wherein each fragment is an elementary discourse unit; and 
 generating a discourse tree that represents rhetorical relationships between the plurality of fragments, wherein the discourse tree comprises a plurality of nodes, each nonterminal node representing a respective rhetorical relationship between two of the plurality of fragments, each terminal node of the nodes of the discourse tree is associated with one of the plurality of fragments. 
 
     
     
       17. The non-transitory computer-readable storage medium of  claim 15 , further comprising:
 determining, based on the one or more links, one or more rhetorical relationships between the first discourse tree and the extended discourse tree; and 
 presenting the rhetorical relationships to a user device. 
 
     
     
       18. The non-transitory computer-readable storage medium of  claim 17 , wherein each rhetorical relationship of the rhetorical relationships comprises one of (i) elaboration, (ii) enablement, (iii) condition, (iv) contrast, or (v) attribution. 
     
     
       19. The non-transitory computer-readable storage medium of  claim 15 , wherein the first document and the second document are obtained by executing a user query of one or more documents. 
     
     
       20. The non-transitory computer-readable storage medium of  claim 15 , wherein the first document and the second document include text based on a particular topic.